{"id":"W4392005731","doi":"10.1016/j.neunet.2024.106199","title":"SecureNet: Proactive intellectual property protection and model security defense for DNNs based on backdoor learning","year":2024,"lang":"en","type":"article","venue":"Neural Networks","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Backdoor; Computer science; Key (lock); License; Computer security; Intellectual property; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001293865,0.0008067226,0.0006337814,0.0005523055,0.0005099764,0.001412413,0.001486198,0.001335021,0.003700046],"category_scores_gemma":[0.002681029,0.0003278346,0.0005972972,0.000285884,0.001208489,0.002979171,0.002503874,0.002132252,0.000832445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009404679,"about_ca_system_score_gemma":0.0014156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001563555,"about_ca_topic_score_gemma":0.002262857,"domain_scores_codex":[0.9993346,0.0001403777,0.00003146747,0.0001442328,0.0002394135,0.00010986],"domain_scores_gemma":[0.9989834,0.0003532614,0.00009144431,0.0003950713,0.0001264484,0.00005023893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001356037,0.0004045461,0.001578066,0.00034868,0.0002874227,0.0004451147,0.000145195,0.5094759,0.04499279,0.1417232,0.02416764,0.2750755],"study_design_scores_gemma":[0.00002911448,0.00008496299,0.00008167226,0.00001494209,0.00001691699,0.00006748338,0.00001047802,0.9583068,0.01344525,0.02522939,0.002700047,0.00001280705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04597669,0.0006543927,0.9340722,0.0007564883,0.0003567364,0.0001330971,0.0003214085,0.01153634,0.006192757],"genre_scores_gemma":[0.8766588,0.0003280595,0.1154771,0.0004974796,0.00007648584,0.00009670302,0.0005060895,0.0004170199,0.005942196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003700046,"threshold_uncertainty_score":0.01237792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02134018583948992,"score_gpt":0.2516275013167942,"score_spread":0.2302873154773043,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}